© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 87077
    Prev
    Next
    INDEX
    Explanations

    creating new arrays and lists

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects code tokens for object or array instantiation—particularly the “new” keyword and data type names like int or String.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     new
    -1.70
     neuen
    -1.13
     جدید
    -1.04
     determina
    -0.97
    新しい
    -0.97
    ใหม่
    -0.96
     nieuwe
    -0.93
    新的
    -0.91
    viamente
    -0.89
     varanda
    -0.88
    POSITIVE LOGITS
    []
    1.19
    []{
    1.05
     enkel
    0.97
     such
    0.94
    such
    0.85
    Such
    0.80
     {
    0.79
     '').
    0.78
     []
    0.78
    ish
    0.78
    Activations Density 0.005%

    No Known Activations